Abstract:We present a model of text analysis for text-to-speech (TTS) synthesis based on (weighted) finite-state transducers, which serves as the text-analysis module of the multilingual Bell Labs TTS system. The transducers are constructed using a lexical toolkit that allows declarative descriptions of lexicons, morphological rules, numeral-expansion rules, and phonological rules, inter alia. To date, the model has been applied to eight languages: Spanish, Italian, Romanian, French, German, Russian, Mandarin and Japan… Show more
“…Text preprocessing is usually a very complex task and includes several language dependent problems (Sproat, 1996). This phase is necessary to clean the texts by removing worthless information, which is of lower value to the text (Karima, Zakaria, & Yamina, 2012).…”
In this paper, an efficient Arabic Expert System for Voice Synthesis, referred to us as AESVS, is proposed. This system, which is based on the Standard Arabic language, consists of 3 phases. The first phase is responsible for the automatic acquisition of human expert knowledge. The acquired knowledge consists of Arabic language pronunciation rules along with the required domain dictionary, to be used by the system. The second phase is concerned with the creation of the sound base that contains the acoustic units needed during the voice generation step. The third phase, which represents the speech synthesis operation, allows the generation of a phonemic sequence for any given word. All words in the input text are converted into their corresponding phonemes sequence by using orthographic phonetic transcription that takes into account their adaptation to the Arabic Language. To ensure this conversion from text to speech, we used approximately 350 predicates created by using the PROLOGUE inference engine, which are stored in a knowledge base that can be used upon request, during both the orthographic–phonetic transcription and the voice generation steps.
“…Text preprocessing is usually a very complex task and includes several language dependent problems (Sproat, 1996). This phase is necessary to clean the texts by removing worthless information, which is of lower value to the text (Karima, Zakaria, & Yamina, 2012).…”
In this paper, an efficient Arabic Expert System for Voice Synthesis, referred to us as AESVS, is proposed. This system, which is based on the Standard Arabic language, consists of 3 phases. The first phase is responsible for the automatic acquisition of human expert knowledge. The acquired knowledge consists of Arabic language pronunciation rules along with the required domain dictionary, to be used by the system. The second phase is concerned with the creation of the sound base that contains the acoustic units needed during the voice generation step. The third phase, which represents the speech synthesis operation, allows the generation of a phonemic sequence for any given word. All words in the input text are converted into their corresponding phonemes sequence by using orthographic phonetic transcription that takes into account their adaptation to the Arabic Language. To ensure this conversion from text to speech, we used approximately 350 predicates created by using the PROLOGUE inference engine, which are stored in a knowledge base that can be used upon request, during both the orthographic–phonetic transcription and the voice generation steps.
“…The first TTS engine that made systematic use of FSTs in all aspects of text normalization was the Bell Labs multilingual text-to-speech synthesizer (Sproat 1996, 1997). In that system, the entire analysis of input text, tokenization, normalization, and conversion to phone sequences was accomplished by a cascaded architecture as depicted in Figure 1.…”
Section: History Of Fst-based Approaches To Text Normalizationmentioning
confidence: 99%
“…The lexical analysis system is more interesting in that it involves: Fig. 1.The text normalization system in the Bell Labs multilingual TTS system (Sproat 1996). Input text is first composed with a lexical analysis transducer, yielding a string of words with possible annotations.…”
Section: History Of Fst-based Approaches To Text Normalizationmentioning
This paper describes the Kestrel text normalization system, a component of the Google textto-speech synthesis (TTS) system. At the core of Kestrel are text-normalization grammars that are compiled into libraries of weighted finite-state transducers (WFSTs). While the use of WFSTs for text normalization is itself not new, Kestrel differs from previous systems in its separation of the initial tokenization and classification phase of analysis from verbalization. Input text is first tokenized and different tokens classified using WFSTs. As part of the classification, detected semiotic classes -expressions such as currency amounts, dates, times, measure phases, are parsed into protocol buffers (https://code.google.com/p/protobuf/). The protocol buffers are then verbalized, with possible reordering of the elements, again using WFSTs. This paper describes the architecture of Kestrel, the protocol buffer representations of semiotic classes, and presents some examples of grammars for various languages. We also discuss applications and deployments of Kestrel as part of the Google TTS system, which runs on both server and client side on multiple devices, and is used daily by millions of people in nineteen languages and counting.
“…In first section we introduced about the need of spellchecker for a Hindi TTS system. In second section we elaborate the methodology used to convert a written text into speech waveform [2]. In section third we provide comparative study to show the effect on phonetic text by adding spellchecker on to input text.…”
Section: Fig 1: Process Of Text To Speech Synthesismentioning
The goal of Text-to-Speech (TTS) synthesis in a particular language is to convert arbitrary input text to intelligible and natural sounding speech. However, for a particular language like Hindi, which is a highly confusing language (due to very close spellings), it is not an easy task to identify errors/mistakes in input text and an incorrect text degrade the quality of output speech hence this paper is a contribution to the development of high quality speech synthesis with the involvement of Spellchecker which generates spell suggestions for misspelled words automatically. Involvement of spellchecker would increase the efficiency of speech synthesis by providing spell suggestions for incorrect input text. Furthermore, we have provided the comparative study for evaluating the resultant effect on to phonetic text by adding spellchecker on to input text.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
